LUAI Challenge 2021 on Learning to Understand Aerial Images

This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV'2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 [7] and GID-15 [35] datasets, this challenge proposes three tasks for oriented object...

Full description

Saved in:
Bibliographic Details
Published in2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) pp. 762 - 768
Main Authors Xia, Gui-Song, Ding, Jian, Qian, Ming, Xue, Nan, Han, Jiaming, Bai, Xiang, Yang, Michael Ying, Li, Shengyang, Belongie, Serge, Luo, Jiebo, Datcu, Mihai, Pelillo, Marcello, Zhang, Liangpei, Zhou, Qiang, Yu, Chao-Hui, Hu, Kaixuan, Bu, Yingjia, Tan, Wenming, Yang, Zhe, Li, Wei, Liu, Shang, Zhao, Jiaxuan, Ma, Tianzhi, Gao, Zi-Han, Wang, Lingqi, Zuo, Yi, Jiao, Licheng, Meng, Chang, Wang, Hao, Wang, Jiahao, Hui, Yiming, Dong, Zhuojun, Zhang, Jie, Bao, Qianyue, Zhang, Zixiao, Liu, Fang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2021
Subjects
Computer vision
Conferences
Image segmentation
Object detection
Semantics
Task analysis
Online AccessGet full text

Cover

More Information
Summary:This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV'2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 [7] and GID-15 [35] datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images.
ISSN:2473-9944
DOI:10.1109/ICCVW54120.2021.00090